[The following was copied and pasted from GPT-4 after I fed it a transcript of a 3 minute ramble I had recorded while walking just now and asked it to turn it into a 500 word blog in the style of Morgan Housel]

Title: Voice to Text: Unleashing Ideas Trapped in the Mind

It seems I've stumbled upon a new method of capturing and nurturing my fleeting thoughts, one that may just revolutionize my approach to idea generation and sharing. This new tool in my arsenal? A humble walk, a recording app, and Google's cutting-edge AI, GPT.

Let me elaborate.

My mind often bustles with thoughts, insights, ideas - fragments of innovation begging to be explored. In the past, I would diligently jot them down in Evernote or Google Drive, bullet point outlines that held the seeds of future blog posts. The intention was always to revisit these thought-germs, to expand them into coherent, engaging stories that I could share with my readers.

Yet, more often than not, these ideas remained confined to their bullet-pointed prisons, unshared, unexplored, unrealized. The connection between conception and fruition seemed to be lost somewhere in my meticulous note-taking and drafting process.

To tackle this, I turned to an unlikely ally: Google's AI. I began recording my thoughts during walks, converting these voice notes to text using Google's transcription services, and pasting this raw, unstructured thought-data into GPT. 

My request to the AI? "Take this and turn it into a 500 word blog post in the style of Morgan Housel." 

If you're unfamiliar with Housel, he's an acclaimed author and blogger who seamlessly blends finance and psychology. His clear, engaging style of storytelling is a masterclass in making complex ideas digestible and, importantly, memorable. Borrowing his writing style might seem ambitious, but remember, our ultimate aim is improvement, and to improve, one must have a model to strive towards.

So, how does this process of idea translation via AI work out?

Interestingly, GPT uses something called "cosine similarity" to decide what comes next. In other words, it measures the cosine of the angle between two vectors in a multi-dimensional space to predict the next word or idea. It's a fascinating melding of linguistics and mathematics.

Is the result perfect? Certainly not. The output is essentially an average of all possible responses based on the AI's estimation of word or idea probabilities. But it is something tangible, a completed work, even if it’s a rough version of what was initially in my mind.

And herein lies the beauty of this process. It bridges the gap between intention and action, between idea and creation. These AI-assisted posts may not be flawless, but they're a significant step up from the dormant bullet points languishing in my digital notes.

This approach has breathed new life into my ideas that were previously resigned to obscurity. I'm unearthing these once-forgotten thoughts and giving them a chance to be seen, read, and perhaps even inspire. I'm taking my implicit ideas, making them explicit, and in the process, creating a trove of thought pieces that, while perhaps not perfect, are undeniably my own.

Because in the end, isn't it better to have something imperfect than nothing at all?

Image Prompt: A robot helping a math teacher with curriculum review

I've had ChatGPT Plus for about 3 months thus far, and I've had a couple spurts of inspiration come and go where I feel like its availability to my curiosity in the moment has been well worth the $60 I've spent on it ($20/month).

• I've gotten some useful R tips and code.
• I've summarized some articles I never got around to reading.
• I've loosely planned multi-stop vacations.
• I've had it explain complex topics to me like I was a 5th grader and create funny analogies.
• I've used it to outline and expand on (and shoot down) some dumb theories I've had.
• I've used it to do some arduous Excel data cleaning and formatting pretty easily.
• Those alone would be worth the $60 thus far on ChatGPT Plus.

But by far I've spent the most time and seen the most value from it helping me with being a math teacher.

Besides thinking of different ways to teach content, coming up with many, many different analogies and real-life examples for the content and skills is a big part of the job for math teachers. Often, the students don't fully understand a topic or skill --EVEN IF they know how to do the math correctly -- until they can relate it to something else outside of classroom - sports, TV/movies, things they've heard about around the dinner table, etc.

They can calculate slope but understand ramps.

They can calculate the roots of a quadratic but understand the flight of a baseball.

They can calculate exponential growth but understand how a virus spreads.

Coming up with many different examples has been very helpful thus far.

The biggest way GPT-4 and various plugins have helped is with lesson plan and curriculum review. Every year I try to do a little revise and review, but mostly this means big picture stuff (curriculum plan, etc.) during the summer and small detail stuff (actual problems in the lesson) during the year, and often the day of or night before. It's that darn procrastination I tell you.

Now with GPT-4 and the Wolfram plugin, I can get many different variations of a math problem instantly. The formatting will make it hard to easily incorporate them into my slides and worksheets but I'll figure that out.

With GPT-4 and the Wolfram plugin, and the prompt below that has been personalized to match the current lesson plan format, I can get lesson plans made for various topics on the spot.

Design an 80-minute Algebra 2 Honors lesson plan on the learning target. The plan should be divided into 5-minute segments and include activities that can be completed on a single sheet of paper. The plan should guide an experienced teacher in introducing the learning goal gradually, and include a list of 5 common student misconceptions. The plan should begin with a review of 3 prerequisite skills, and end with a list of 3 skills that could be learned next. The lesson should start with a 5-minute activity that reviews prerequisite skills, then balance instruction and practice, with practice time being three times instruction time. The lesson should end with a 5-minute summary and a 5-minute formative assessment. The plan should include 3 example problems in each section that align with the learning goal, and 3 assessment problems that could appear on a summative assessment. The total time should be 80 minutes. This lesson’s learning target is: XXX

With GPT-4, I've been able to easily and quickly (albeit roughly) think up a year's worth of curriculum planning for a new subject I'll be teaching in the fall, Statistics & Probability. Obviously I'll lean on previous curricula and established AP/IB topics and pacing, but GPT has been able to explain things in more detail that I'm not familiar with and even is helping me create a week-by-week breakdown. This could have all happened without GPT but it has been much easier and quicker with the help of AI.

More recently, with GPT-4 and the Wolfram + Link Reader plugins, I've been surprised and excited that I could review, summarize, and suggest improvements for my classroom presentation slides! This is a big deal, because even though it won't do a fantastic job, a good enough job is better than anything I could do in the same amount of time. To do so, this was the process I followed:

1. Go to Google Drive and make each presentation shareable with a link

2. Copy the link

3. Paste the link at the end of a customized prompt that reviewed, summarized, and suggested improvements (below)

4. Copy and paste the answers from GPT-4 in a Google Doc

The prompt I used was based on chain-of-thought, self-critique, and expert planning and can be found below. It was good, not great, and can be improved:

Let's go through the presentation linked below together.

First, start by summarizing the key points from the presentation. After that, proceed through the presentation and summarize the main learnings from it. Finally, provide an enticing overall summary, make it compelling for the reader, and suggest ways to improve the presentation.

Second, critique your own summary. Does it accurately reflect the main points of the presentation? Is it compelling enough to make someone want to read the presentation? What improvements can be made to the summary?

Third, imagine how experts in math pedagogy and teaching, like Jo Boaler and Sal Khan, would summarize and critique this linked presentation. What key points would they focus on? What aspects of the presentation might they suggest to improve for better understanding?

Finally, synthesize all of those points above into one coherent and beautiful answer. Then provide your 3 biggest improvements you would make to either the flow of information or to the presentation to improve the student's understanding of the topic and include 3 examples of each of the improvements.

The linked presentation is: XXX

Again, even though these summaries and answers weren't perfect, they were good. And I can work with good.

I took my Google Doc of all the answers and cleaned it up, removing the repeated AI responses, until I had a Doc just of topics covered and improvements suggested per lesson. Most of the improvements were centered around more visual aids and graphics, more interactive tools, and activities that would increase student participation.

Then I used this prompt below and customized it with each lesson's topics and improvements for an expanded list of improvements for the topics that GPT-4 pulled out of the presentation links I fed it. The prompt is:

You are an AI program that is designed to create the world’s most fun, interesting, and informative math lessons for high schoolers. The lessons are not in the exact style of but are similar to Richard Feynman’s famous physics lectures. Above all, these lessons should be relatable to the students' lives so that the students care more about them. 

Imagine a lesson plan that covers these topics:

XXX

and give me at least 20 specific examples or math problems that would make this the world’s best math lesson and are similar to these:

XXX

A lot of the improvements suggested won't be used, but some will. And that's some more than I probably would have updated it with. So, all in all, it was a nice way to get an outsider's perspective on the topics covered and to generate some additional ideas for ways to communicate the learnings and skills.

I plan to review the answers, revise them, and to keep experimenting with different ways of getting better.

GPT-4 is not perfect. But neither am I.

I wanted to continue what has become a yearly tradition in looking at NFL Draft visits by team and position. As I have done in years past, the data was pulled from Walter Football and is current as of April 19, 2023. Visits should be ending soon so this is almost a complete list that is available to the public, as a lot of teams are pretty secretive about their visits getting out. But some beat reporter sleuthing and agent promoting has gotten us to this point.

Similar to last year, I assigned points to each type of visit per prospect (ex. virtual visit just worth 1 point, a private workout worth 3 points) and then tallied the total points across a position. Because while an individual prospect's agent might be more promotional than another's, across the board some patterns should emerge by position.

• Visits worth 1 point = visits where the teams were already there and just talked to a player = Senior Bowl visit, NFL Combine visit, virtual visit
• Visits worth 2 points = visits where the team sought out the player, but in a group setting = Pro Day visit, Local visits (players that grew up or went to college in the area)
• Visits worth 3 points = individual visits where the player was brought in or worked out, often the most important = Private visits (teams have 30 of these to use), Workout visits

(the spreadsheet is conditionally formatted by color by position, so a darker color means that particular team paid more attention to that specific position more than other teams)

As I have done in previous years, I took a look at aggregating NFL Draft prospect team visits via Walter Football. This year, I awarded points per visit as: 1 point for a virtual or Senior Bowl meeting, 2 points for a Pro Day, Combine, or local prospect meeting, and 3 points for a private visit or workout. This is obviously not an exhaustive list -- as it doesn't include ALL visits, if they weren't reported by the team or if an agent does a better job of broadcasting their clients' visits -- but it does likely lead to team/position insights and can't be dismissed.

Here is the breakdown of visit points per position per team, with the cells conditionally formatted to be darker green if the team has spent more visit points on certain positions over others:

Also, here is my final mock draft for 2022. I wanted to project trades but it becomes too complex too quickly to do that.

Step back from the ledge, Chiefs Kingdom.

I know it hurts to see one of your own suddenly taken from you. I realize it pains to see a future you had in mind suddenly vanish.

Today is a day for being sad. You’re allowed to be sad. It doesn’t have to make sense today, sadness makes sense.

So read this tomorrow. Always tomorrow. 

The prospect of tomorrow brings optimism – and sadness is bad, whereas optimism is good.

Today: sadness. Tomorrow: optimism. 

Somewhere in between realism sets in that it was inevitable that the Holy Passing Trinity of Patrick Mahomes + Tyreek Hill + Travis Kelce would break up. But we all thought they had a couple more years together, at least! We all thought we had a couple more years together, at least.

We thought they’d break up tomorrow, not today. We thought we’d break up tomorrow, not today.

But, unfortunately, sadness doesn’t come tomorrow. The sickle of sadness comes today.

Tomorrow is for optimism. 

Optimism that maybe defenses really had figured out how to stop the Holy Passing Trinity + Band of Others and that – maybe, just maybe – the passing attack needed to be blown up. (Whaaaaaaaat! *gasp*)

Not today though, we hoped. Blown up tomorrow. Maybe.

Maybe we could get a player or two in free agency + the draft and keep the Holy Passing Trinity together and actually improve! I mean, yeah, that would require all three of the aerial triumvirate to be happy with their contracts + require hitting on that other free agent (JuJu) + draft pick (?). And the former would hinge on Hill agreeing to an extension.

But… Hill didn’t want to agree to KC’s extension. Uh oh. 

He wasn’t supposed to tell us that! Not today, at least. Tell us that tomorrow.

The reality is that Tyreek saw others getting more money and wanted to be compensated similarly. Which is… fair? KC could always pay him more money, of course, and push off salary cap pain to future years. They wouldn’t ever really have to face the financial music, because the cap isn’t real. 

The cap isn’t real…right? RIGHT?!?

We wouldn’t have to find out if the cap was real or not today at least. Tomorrow, maybe.

So what was Brett Veach & Co. supposed to do? Well, we saw today what leaders do in tough situations: they don’t push off making hard decisions until tomorrow, they know the best time – hell, the only time – to deal with tough situations is now. Right now. Today.

Make the hard decision today, pay the price today, be sad/mad/angry today. You’ll be happier tomorrow.

Tomorrow is for optimism, today is for sadness.

Tomorrow is for moving on, today is for breaking up.

Tomorrow is for looking at WR draft highlights, today is for looking at Hill’s Chiefs highlights.

Tomorrow we’ll talk about how this draft is loaded with legit starting potential in rounds 2, 3, and 4 (picks 33-143, or 111 in total) and how now the Chiefs have 8 (EIGHT!) of those 111, including numbers 29 and 30 with 5th year options. 

With 32 NFL teams, you would expect 3.47 picks per team in that 111 pick range, giving the Chiefs over double the amount of picks that you’d expect. In one of the deepest drafts for WR/CB/DE/LB/OT in recent memory (all areas the Chiefs need help).

We’ll talk about all those things tomorrow. Today, we mourn.

Today, sadness. Tomorrow, optimism.